Full Length Article
DOI: https://doi.org/10.54216/JIER.030205
A Dual-Bank Hybrid Predictive Model (DBHPM) for Financial Forecasting
Forecasting financial performance is important for strategy formulation and identifying potential problems in banking institutions. This paper presents the Dual-Bank Hybrid Predictive Model (DBHPM), a financial forecasting model combining Multiple Linear Regression (MLR) and Random Forest Regression (RFR). It is validated on two actual financial datasets from Agrobank and NBU Bank covering 2021–2025. The model analyzes financial indicators including net profit, equity, and solvency, and forecasts them through 2027. Specifically, DBHPM uses MLR for linear modeling in the first step and RFR for nonlinear residuals in the second step; the paper reports stronger generalization and predictive strength than using the latter stage alone. Experiments show that DBHPM minimizes MAE and RMSE and achieves a coefficient of determination (R2) of 0.95 or above compared with models trained independently. The forecasts indicate net profit of approximately 1.18 billion sum for Agrobank and 3.66 billion sum for NBU Bank by the end of 2027. The proposed hybrid model supports predictive financial analysis for decision-making, risk awareness, and economic forecasting in the banking industry.
Samandarboy Sulaymanov
visibility
1055
download
628